/*
* SetTransactionSnapshot
* Set the transaction's snapshot from an imported MVCC snapshot.
*
* Note that this is very closely tied to GetTransactionSnapshot --- it
* must take care of all the same considerations as the first-snapshot case
* in GetTransactionSnapshot.
*/
static void
SetTransactionSnapshot(Snapshot sourcesnap, TransactionId sourcexid)
{
/* Caller should have checked this already */
Assert(!FirstSnapshotSet);
Assert(RegisteredSnapshots == 0);
Assert(FirstXactSnapshot == NULL);
/*
* Even though we are not going to use the snapshot it computes, we must
* call GetSnapshotData, for two reasons: (1) to be sure that
* CurrentSnapshotData's XID arrays have been allocated, and (2) to update
* RecentXmin and RecentGlobalXmin. (We could alternatively include those
* two variables in exported snapshot files, but it seems better to have
* snapshot importers compute reasonably up-to-date values for them.)
*/
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/*
* Now copy appropriate fields from the source snapshot.
*/
CurrentSnapshot->xmin = sourcesnap->xmin;
CurrentSnapshot->xmax = sourcesnap->xmax;
CurrentSnapshot->xcnt = sourcesnap->xcnt;
Assert(sourcesnap->xcnt <= GetMaxSnapshotXidCount());
memcpy(CurrentSnapshot->xip, sourcesnap->xip,
sourcesnap->xcnt * sizeof(TransactionId));
CurrentSnapshot->subxcnt = sourcesnap->subxcnt;
Assert(sourcesnap->subxcnt <= GetMaxSnapshotSubxidCount());
memcpy(CurrentSnapshot->subxip, sourcesnap->subxip,
sourcesnap->subxcnt * sizeof(TransactionId));
CurrentSnapshot->suboverflowed = sourcesnap->suboverflowed;
CurrentSnapshot->takenDuringRecovery = sourcesnap->takenDuringRecovery;
/* NB: curcid should NOT be copied, it's a local matter */
/*
* Now we have to fix what GetSnapshotData did with MyProc->xmin and
* TransactionXmin. There is a race condition: to make sure we are not
* causing the global xmin to go backwards, we have to test that the
* source transaction is still running, and that has to be done atomically.
* So let procarray.c do it.
*
* Note: in serializable mode, predicate.c will do this a second time.
* It doesn't seem worth contorting the logic here to avoid two calls,
* especially since it's not clear that predicate.c *must* do this.
*/
if (!ProcArrayInstallImportedXmin(CurrentSnapshot->xmin, sourcexid))
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("could not import the requested snapshot"),
errdetail("The source transaction %u is not running anymore.",
sourcexid)));
/*
* In transaction-snapshot mode, the first snapshot must live until end of
* xact, so we must make a copy of it. Furthermore, if we're running in
* serializable mode, predicate.c needs to do its own processing.
*/
if (IsolationUsesXactSnapshot())
{
if (IsolationIsSerializable())
SetSerializableTransactionSnapshot(CurrentSnapshot, sourcexid);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
RegisteredSnapshots++;
}
FirstSnapshotSet = true;
}
/*
* ImportSnapshot
* Import a previously exported snapshot. The argument should be a
* filename in SNAPSHOT_EXPORT_DIR. Load the snapshot from that file.
* This is called by "SET TRANSACTION SNAPSHOT 'foo'".
*/
void
ImportSnapshot(const char *idstr)
{
char path[MAXPGPATH];
FILE *f;
struct stat stat_buf;
char *filebuf;
int xcnt;
int i;
TransactionId src_xid;
Oid src_dbid;
int src_isolevel;
bool src_readonly;
SnapshotData snapshot;
/*
* Must be at top level of a fresh transaction. Note in particular that
* we check we haven't acquired an XID --- if we have, it's conceivable
* that the snapshot would show it as not running, making for very
* screwy behavior.
*/
if (FirstSnapshotSet ||
GetTopTransactionIdIfAny() != InvalidTransactionId ||
IsSubTransaction())
ereport(ERROR,
(errcode(ERRCODE_ACTIVE_SQL_TRANSACTION),
errmsg("SET TRANSACTION SNAPSHOT must be called before any query")));
/*
* If we are in read committed mode then the next query would execute
* with a new snapshot thus making this function call quite useless.
*/
if (!IsolationUsesXactSnapshot())
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("a snapshot-importing transaction must have isolation level SERIALIZABLE or REPEATABLE READ")));
/*
* Verify the identifier: only 0-9, A-F and hyphens are allowed. We do
* this mainly to prevent reading arbitrary files.
*/
if (strspn(idstr, "0123456789ABCDEF-") != strlen(idstr))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid snapshot identifier \"%s\"", idstr)));
/* OK, read the file */
snprintf(path, MAXPGPATH, SNAPSHOT_EXPORT_DIR "/%s", idstr);
f = AllocateFile(path, PG_BINARY_R);
if (!f)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid snapshot identifier \"%s\"", idstr)));
/* get the size of the file so that we know how much memory we need */
if (fstat(fileno(f), &stat_buf))
elog(ERROR, "could not stat file \"%s\": %m", path);
/* and read the file into a palloc'd string */
filebuf = (char *) palloc(stat_buf.st_size + 1);
if (fread(filebuf, stat_buf.st_size, 1, f) != 1)
elog(ERROR, "could not read file \"%s\": %m", path);
filebuf[stat_buf.st_size] = '\0';
FreeFile(f);
/*
* Construct a snapshot struct by parsing the file content.
*/
memset(&snapshot, 0, sizeof(snapshot));
src_xid = parseXidFromText("xid:", &filebuf, path);
/* we abuse parseXidFromText a bit here ... */
src_dbid = parseXidFromText("dbid:", &filebuf, path);
src_isolevel = parseIntFromText("iso:", &filebuf, path);
src_readonly = parseIntFromText("ro:", &filebuf, path);
snapshot.xmin = parseXidFromText("xmin:", &filebuf, path);
snapshot.xmax = parseXidFromText("xmax:", &filebuf, path);
snapshot.xcnt = xcnt = parseIntFromText("xcnt:", &filebuf, path);
/* sanity-check the xid count before palloc */
if (xcnt < 0 || xcnt > GetMaxSnapshotXidCount())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid snapshot data in file \"%s\"", path)));
snapshot.xip = (TransactionId *) palloc(xcnt * sizeof(TransactionId));
for (i = 0; i < xcnt; i++)
snapshot.xip[i] = parseXidFromText("xip:", &filebuf, path);
snapshot.suboverflowed = parseIntFromText("sof:", &filebuf, path);
if (!snapshot.suboverflowed)
{
snapshot.subxcnt = xcnt = parseIntFromText("sxcnt:", &filebuf, path);
/* sanity-check the xid count before palloc */
if (xcnt < 0 || xcnt > GetMaxSnapshotSubxidCount())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid snapshot data in file \"%s\"", path)));
snapshot.subxip = (TransactionId *) palloc(xcnt * sizeof(TransactionId));
for (i = 0; i < xcnt; i++)
snapshot.subxip[i] = parseXidFromText("sxp:", &filebuf, path);
}
else
{
snapshot.subxcnt = 0;
snapshot.subxip = NULL;
}
snapshot.takenDuringRecovery = parseIntFromText("rec:", &filebuf, path);
/*
* Do some additional sanity checking, just to protect ourselves. We
* don't trouble to check the array elements, just the most critical
* fields.
*/
if (!TransactionIdIsNormal(src_xid) ||
!OidIsValid(src_dbid) ||
!TransactionIdIsNormal(snapshot.xmin) ||
!TransactionIdIsNormal(snapshot.xmax))
ereport(ERROR,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("invalid snapshot data in file \"%s\"", path)));
/*
* If we're serializable, the source transaction must be too, otherwise
* predicate.c has problems (SxactGlobalXmin could go backwards). Also,
* a non-read-only transaction can't adopt a snapshot from a read-only
* transaction, as predicate.c handles the cases very differently.
*/
if (IsolationIsSerializable())
{
if (src_isolevel != XACT_SERIALIZABLE)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("a serializable transaction cannot import a snapshot from a non-serializable transaction")));
if (src_readonly && !XactReadOnly)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("a non-read-only serializable transaction cannot import a snapshot from a read-only transaction")));
}
/*
* We cannot import a snapshot that was taken in a different database,
* because vacuum calculates OldestXmin on a per-database basis; so the
* source transaction's xmin doesn't protect us from data loss. This
* restriction could be removed if the source transaction were to mark
* its xmin as being globally applicable. But that would require some
* additional syntax, since that has to be known when the snapshot is
* initially taken. (See pgsql-hackers discussion of 2011-10-21.)
*/
if (src_dbid != MyDatabaseId)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot import a snapshot from a different database")));
/* OK, install the snapshot */
SetTransactionSnapshot(&snapshot, src_xid);
}
/* Merge local and global snapshots.
* Produce most restricted (conservative) snapshot which treate transaction as in-progress if is is marked as in-progress
* either in local, either in global snapshots
*/
static void DtmMergeWithGlobalSnapshot(Snapshot dst)
{
int i, j, n;
TransactionId xid;
Snapshot src = &DtmSnapshot;
if (!(TransactionIdIsValid(src->xmin) && TransactionIdIsValid(src->xmax))) {
PgGetSnapshotData(dst);
return;
}
GetLocalSnapshot:
/*
* Check that global and local snapshots are consistent: transactions marked as completed in global snapshot
* should be completed locally
*/
dst = PgGetSnapshotData(dst);
for (i = 0; i < dst->xcnt; i++)
if (TransactionIdIsInDoubt(dst->xip[i]))
goto GetLocalSnapshot;
for (xid = dst->xmax; xid < src->xmax; xid++)
if (TransactionIdIsInDoubt(xid))
goto GetLocalSnapshot;
GetCurrentTransactionId();
DumpSnapshot(dst, "local");
DumpSnapshot(src, "DTM");
if (src->xmax < dst->xmax) dst->xmax = src->xmax;
if (src->xmin < dst->xmin) dst->xmin = src->xmin;
Assert(src->subxcnt == 0);
if (src->xcnt + dst->subxcnt + dst->xcnt <= GetMaxSnapshotXidCount())
{
Assert(dst->subxcnt == 0);
memcpy(dst->xip + dst->xcnt, src->xip, src->xcnt*sizeof(TransactionId));
n = dst->xcnt + src->xcnt;
qsort(dst->xip, n, sizeof(TransactionId), xidComparator);
xid = InvalidTransactionId;
for (i = 0, j = 0; i < n && dst->xip[i] < dst->xmax; i++)
if (dst->xip[i] != xid)
dst->xip[j++] = xid = dst->xip[i];
dst->xcnt = j;
}
else
{
Assert(src->xcnt + dst->subxcnt + dst->xcnt <= GetMaxSnapshotSubxidCount());
memcpy(dst->subxip + dst->subxcnt, dst->xip, dst->xcnt*sizeof(TransactionId));
memcpy(dst->subxip + dst->subxcnt + dst->xcnt, src->xip, src->xcnt*sizeof(TransactionId));
n = dst->xcnt + dst->subxcnt + src->xcnt;
qsort(dst->subxip, n, sizeof(TransactionId), xidComparator);
xid = InvalidTransactionId;
for (i = 0, j = 0; i < n && dst->subxip[i] < dst->xmax; i++)
if (dst->subxip[i] != xid)
dst->subxip[j++] = xid = dst->subxip[i];
dst->subxcnt = j;
dst->xcnt = 0;
}
DumpSnapshot(dst, "merged");
}